# Cross-conditioned Diffusion Model for Medical Image to Image Translation

arXiv: https://arxiv.org/abs/2409.08500 · HTML: https://mlsanity.com/paper/2409.08500/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 13 Sep 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Understanding and Improving Layer Normalization](https://mlsanity.com/paper/1911.07013/) (2019)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1809.05852/) (2018)
- [Breaking the Dilemma of Medical Image-to-image Translation](https://mlsanity.com/paper/2110.06465/) (2021)
- [The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)](https://mlsanity.com/paper/2305.17033/) (2023)
- [Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation](https://mlsanity.com/paper/2303.10326/) (2023)
- [NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation](https://mlsanity.com/paper/2208.14876/) (2022)
- [SegRap2023: A Benchmark of Organs-at-Risk and Gross Tumor Volume Segmentation for Radiotherapy Planning of Nasopharyngeal Carcinoma](https://mlsanity.com/paper/2312.09576/) (2023)
- [Contrastive Registration for Unsupervised Medical Image Segmentation](https://mlsanity.com/paper/2011.08894/) (2020)
- [SCOTCH and SODA: A Transformer Video Shadow Detection Framework](https://mlsanity.com/paper/2211.06885/) (2022)
- [Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration](https://mlsanity.com/paper/1907.01922/) (2019)
- [TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM](https://mlsanity.com/paper/2406.15764/) (2024)
- [HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation](https://mlsanity.com/paper/2303.10333/) (2023)
- [Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge](https://mlsanity.com/paper/2312.13752/) (2023)
- [Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset](https://mlsanity.com/paper/2406.13645/) (2024)
- [Diffusion Model Driven Test-Time Image Adaptation for Robust Skin Lesion Classification](https://mlsanity.com/paper/2405.11289/) (2024)

## Built on by (most cited first, 26 of 26)

- [Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning](https://mlsanity.com/paper/2506.02327/) (2025)
- [Regression is all you need for medical image translation](https://mlsanity.com/paper/2505.02048/) (2025)
- [Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline](https://mlsanity.com/paper/2506.05175/) (2025)
- [AMM-Diff: Adaptive Multi-Modality Diffusion Network for Missing Modality Imputation](https://mlsanity.com/paper/2501.12840/) (2025)
- [Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging](https://mlsanity.com/paper/2504.08635/) (2025)
- [Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation](https://mlsanity.com/paper/2411.06106/) (2024)
- [Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis](https://mlsanity.com/paper/2505.17333/) (2025)
- [Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation](https://mlsanity.com/paper/2601.18623/) (2026)
- [ImmunoDiff: A Diffusion Model for Immunotherapy Response Prediction in Lung Cancer](https://mlsanity.com/paper/2505.23675/) (2025)
- [Generative Drifting for Conditional Medical Image Generation](https://mlsanity.com/paper/2604.19736/) (2026)
- [Bidirectional Mammogram View Translation with Column-Aware and Implicit 3D Conditional Diffusion](https://mlsanity.com/paper/2510.04947/) (2025)
- [Curvilinear Structure-preserving Unpaired Cross-domain Medical Image Translation](https://mlsanity.com/paper/2510.19679/) (2025)
- [Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention](https://mlsanity.com/paper/2605.06699/) (2026)
- [Enhancing Product Search Interfaces with Sketch-Guided Diffusion and Language Agents](https://mlsanity.com/paper/2504.08739/) (2025)
- [Mitigating 3D Prostate Biparametric MRI Data Scarcity through Domain Adaptation using Locally-Trained Latent Diffusion Models for Prostate Cancer Detection](https://mlsanity.com/paper/2507.06384/) (2025)
- [K-Stain: Keypoint-Driven Correspondence for H&E-to-IHC Virtual Staining](https://mlsanity.com/paper/2511.06709/) (2025)
- [ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion](https://mlsanity.com/paper/2511.17068/) (2025)
- [A-QCF-Net: An Adaptive Quaternion Cross-Fusion Network for Multimodal Liver Tumor Segmentation from Unpaired Datasets](https://mlsanity.com/paper/2512.21760/) (2025)
- [Towards Personalized Multi-Modal MRI Synthesis across Heterogeneous Datasets](https://mlsanity.com/paper/2602.19723/) (2026)
- [OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction](https://mlsanity.com/paper/2603.22421/) (2026)
- [HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling](https://mlsanity.com/paper/2603.23041/) (2026)
- [3D Ultrasound-Derived Pseudo-CT Synthesis Using a Transformer-Augmented Residual Network for Real-Time Operator Guidance](https://mlsanity.com/paper/2605.04856/) (2026)
- [Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation](https://mlsanity.com/paper/2606.24313/) (2026)
- [Do Not Break the Vessels: Structure-Preserving Mean Flow for Vascular Image Translation](https://mlsanity.com/paper/2606.31095/) (2026)
- [Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation](https://mlsanity.com/paper/2607.07401/) (2026)
- [Spectral Consistent Flow for One-step 3D Medical Image Translation](https://mlsanity.com/paper/2607.10627/) (2026)

## Abstract (arXiv)

Multi-modal magnetic resonance imaging (MRI) provides rich, complementary information for analyzing diseases. However, the practical challenges of acquiring multiple MRI modalities, such as cost, scan time, and safety considerations, often result in incomplete datasets. This affects both the quality of diagnosis and the performance of deep learning models trained on such data. Recent advancements in generative adversarial networks (GANs) and denoising diffusion models have shown promise in natural and medical image-to-image translation tasks. However, the complexity of training GANs and the computational expense associated with diffusion models hinder their development and application in this task. To address these issues, we introduce a Cross-conditioned Diffusion Model (CDM) for medical image-to-image translation. The core idea of CDM is to use the distribution of target modalities as guidance to improve synthesis quality while achieving higher generation efficiency compared to conventional diffusion models. First, we propose a Modality-specific Representation Model (MRM) to model the distribution of target modalities. Then, we design a Modality-decoupled Diffusion Network (MDN) to efficiently and effectively learn the distribution from MRM. Finally, a Cross-conditioned UNet (C-UNet) with a Condition Embedding module is designed to synthesize the target modalities with the source modalities as input and the target distribution for guidance. Extensive experiments conducted on the BraTS2023 and UPenn-GBM benchmark datasets demonstrate the superiority of our method.